Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 923 941 902 937 903 253  94 438 536 321 156 538 169 455 950 975 186 139 211 761
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 253 950  NA 923 186 902 975 538 169  94 211  NA 455 156 903 321 937 438 761 941 536  NA 139
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 3 4 4 1 2 2 5 2 2
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "i" "z" "e" "w" "u" "T" "M" "C" "G" "S"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  1  2  3  4  5 15 16
which( manyNumbersWithNA > 900 )
[1]  2  4  6  7 15 17 20
which( is.na( manyNumbersWithNA ) )
[1]  3 12 22

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 923 941 902 937 903 950 975
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 923 941 902 937 903 950 975
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 923 941 902 937 903 950 975

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "T" "M" "C" "G" "S"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "i" "z" "e" "w" "u"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  8  9 10 12 14
sum( manyNumbers %in% 300:600 )
[1] 5

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "large" NA      "large" "small" "large" "large" "large" "small" "small" "small" NA      "small" "small" "large" "small"
[17] "large" "small" "large" "large" "large" NA      "small"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "large"   "UNKNOWN" "large"   "small"   "large"   "large"   "large"   "small"   "small"   "small"   "UNKNOWN" "small"  
[14] "small"   "large"   "small"   "large"   "small"   "large"   "large"   "large"   "UNKNOWN" "small"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0 950  NA 923   0 902 975 538   0   0   0  NA   0   0 903   0 937   0 761 941 536  NA   0

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 1 3 4 2 5
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  3  4  2  5
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE  TRUE FALSE  TRUE FALSE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 7
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 975
which.min( manyNumbersWithNA )
[1] 10
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 94
range( manyNumbersWithNA, na.rm = TRUE )
[1]  94 975

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 253 950  NA 923 186 902 975 538 169  94 211  NA 455 156 903 321 937 438 761 941 536  NA 139
sort( manyNumbersWithNA )
 [1]  94 139 156 169 186 211 253 321 438 455 536 538 761 902 903 923 937 941 950 975
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  94 139 156 169 186 211 253 321 438 455 536 538 761 902 903 923 937 941 950 975  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 975 950 941 937 923 903 902 761 538 536 455 438 321 253 211 186 169 156 139  94  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 253 950  NA 923 186
order( manyNumbersWithNA[1:5] )
[1] 5 1 4 2 3
rank( manyNumbersWithNA[1:5] )
[1] 2 4 5 3 1
sort( mixedLetters )
 [1] "C" "e" "G" "i" "M" "S" "T" "u" "w" "z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 9.5 5.5 8.0 2.5 5.5 2.5 2.5 2.5 7.0 9.5
rank( manyDuplicates, ties.method = "min" )
 [1] 9 5 8 1 5 1 1 1 7 9
rank( manyDuplicates, ties.method = "random" )
 [1]  9  6  8  3  5  1  4  2  7 10

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000  0.29462018  0.32483471 -0.25245818  0.96672018  1.06404391
[11]  0.15778373 -0.24556289 -1.00765411  0.09605385  0.45548199
round( v, 0 )
 [1] -1  0  0  0  1  0  0  0  1  1  0  0 -1  0  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.3  0.3 -0.3  1.0  1.1  0.2 -0.2 -1.0  0.1  0.5
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.29  0.32 -0.25  0.97  1.06  0.16 -0.25 -1.01  0.10  0.46
floor( v )
 [1] -1 -1  0  0  1  0  0 -1  0  1  0 -1 -2  0  0
ceiling( v )
 [1] -1  0  0  1  1  1  1  0  1  2  1  0 -1  1  1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC